Optimization of Fingerprint Matching Localization Algorithm Based on RSSI in Wireless Sensor Network

Wireless Sensor Networks (WSNs) are a crucial component of modern information technology and are widely used in applications such as environmental monitoring, smart homes, and healthcare. Node localization technology is fundamental to the operation of these applications. Because traditional received signal strength indicator (RSSI) fingerprint matching localization algorithms face significant challenges in practical applications, such as low positioning accuracy and high computational complexity, this paper proposes an optimized method for RSSI-based fingerprint matching localization in WSNs, which enhances effectiveness and expands application scope. Firstly, Kalman filtering is applied to preprocess RSSI values, reducing noise interference. Secondly, the RSSI distance model is used to construct fingerprint node circles, forming a fingerprint database and lessening the data required for matching. Finally, Dynamic Time Warping (DTW) distance measures the similarity between positioning points and fingerprint data nodes, significantly enhancing the accuracy and precision of the matching process. In addition, the optimized algorithm also supports collaborative localization between multiple agents, so as to achieve real-time tracking and positioning of objects in space. The simulation and experimental results indicate that the algorithm delivers remarkable performance in two-dimensional and three-dimensional localization, with a 93% improvement in positioning accuracy and a nearly tenfold boost in computational efficiency.